aiqbench analysis
ExpertoRhythm introduces a morphology-aware learning objective within an attention-enhanced 1D U-Net to reconstruct arterial blood pressure waveforms from single-channel PPG signals. By integrating range-weighted loss functions, the model achieves clinically significant accuracy that outperforms standard MSE approaches across diverse pressure ranges up to 200 mmHg. This work advances the feasibility of continuous, cuffless blood pressure monitoring for wearable health applications through specialized deep learning architectures.
ExpertoRhythm: Morphology-Aware Learning for Waveform Reconstruction and Cuffless Blood Pressure Estimation from Single-Channel PPG
arXiv:2609.34146v1 Announce Type: new Abstract: Continuous cuffless blood pressure (BP) monitoring from photoplethysmography (PPG) has strong potential for wearable health and telemonitoring, but accurate estimation remains difficult because PPG-to-BP mapping must preserve subtle waveform morphology and pressure-range-dependent dynamics. We introduce ExpertoRhythm, an attention-enhanced 1D U-Net that reconstructs the arterial blood pressure (ABP) waveform from a single-channel PPG signal and derives systolic and diastolic BP directly from the reconstructed waveform. The central contribution is a composite morphology-aware learning objective that integrates range-weighted SmoothL1 reconstruction with a window-range regularizer to emphasize high-dynamic BP segments and reduce amplitude under/over-shoot. On the UCI cuff-less BP dataset with 942 subjects, ExpertoRhythm achieves 2.46/1.46 mmHg MAE for systolic/diastolic BP (SBP/DBP), while obtaining a 30.4% average relative error reduction over pure MSE across waveform reconstruction and BP estimation metrics. Clinical-style evaluation further demonstrates low bias and strong agreement across the BP range, including high-pressure windows up to 200 mmHg, satisfying AAMI criteria and achieving BHS Grade A. These results suggest that morphology-aware waveform reconstruction from a single PPG channel can provide an accurate and practical pathway toward continuous cuffless BP monitoring in wearable and remote-care settings.
Abstract:Continuous cuffless blood pressure (BP) monitoring from photoplethysmography (PPG) has strong potential for wearable health and telemonitoring, but accurate estimation remains difficult because PPG-to-BP mapping must preserve subtle waveform morphology and pressure-range-dependent dynamics. We introduce ExpertoRhythm, an attention-enhanced 1D U-Net that reconstructs the arterial blood pressure (ABP) waveform from a single-channel PPG signal and derives systolic and diastolic BP directly from the reconstructed waveform. The central contribution is a composite morphology-aware learning objective that integrates range-weighted SmoothL1 reconstruction with a window-range regularizer to emphasize high-dynamic BP segments and reduce amplitude under/over-shoot. On the UCI cuff-less BP dataset with 942 subjects, ExpertoRhythm achieves 2.46/1.46 mmHg MAE for systolic/diastolic BP (SBP/DBP), while obtaining a 30.4% average relative error reduction over pure MSE across waveform reconstruction and BP estimation metrics. Clinical-style evaluation further demonstrates low bias and strong agreement across the BP range, including high-pressure windows up to 200 mmHg, satisfying AAMI criteria and achieving BHS Grade A. These results suggest that morphology-aware waveform reconstruction from a single PPG channel can provide an accurate and practical pathway toward continuous cuffless BP monitoring in wearable and remote-care settings.
Machine Learning (cs.LG)
arXiv:2609.34146 [cs.LG]
(or arXiv:2609.34146v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2609.34146 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 278 words
Related coverage
DMT: Demographic Conditioning, Morphology-Enhanced Transformer for Cuffless Blood Pressure Estimation from PPG Signals
arXiv · Jun 10, 2026
Blood Pressure Estimation from PPG: A Comparative Study of Direct and ECG-Mediated Deep Learning Pipelines
arXiv · Jul 28, 2026
Survey of Novel Deep Learning Architectures for Denoising Gravitational-wave Signals
arXiv · Sep 15, 2026
Reconstructing Synthetic SDO/AIA 193 A EUV Images from He I 10830 A Observations with Diffusion Model Translator
arXiv · Jun 9, 2026